Abstract
Electroencephalogram (EEG) is one of the fundamental tools for analyzing the behavior of brain and particularly helpful for treatment of epilepsy and detection of associated seizures. For long-term recording of EEG signals, current research is heading towards simple, unobtrusive and ambulatory devices with a small number of channels. The primary contribution of this paper is to assess the performance difference between the seizure detection results using features from all channels versus only the channels in/around the temporal region. For this purpose, we develop a supervised seizure detection algorithm that uses time domain features extracted sequentially for every 1-second epoch. By using this algorithm, we obtained sensitivity values of 0.95 and 0.92, specificity values of 0.99 and 0.99 and false positive per hour values as 0.16 and 0.21 for all 23 channels and 10 temporal region channels, respectively. These results show that restricting the EEG analysis to temporal region results only in a graceful and gradual degradation of classifier performance. We conclude that EEG ambulatory devices with a montage local to the temporal region could demonstrate satisfactory performance. This presents a promising way forward for the use of ambulatory devices with compact wearable design.
Highlights
Epilepsy is one of the most common and chronic disorders of the brain
True positive (TP) is the counter that increments when the algorithm chooses a positive outcome and it coincides with the positive detection in the ground truth
We assume a TP event has occurred, if the positive labels epochs are detected for N consecutive epochs in a time window beginning from 1 minute prior to the start of the seizure and ending at 1 minute after the end of seizure
Summary
Epilepsy is one of the most common and chronic disorders of the brain. About 1% of the world population is reported to be suffering from this disease [1]. Epilepsy has been around since recorded history and has been treated according to the techniques and technology in vogue, e.g., trephining. With the passage of time and advancement in medical science and technology, different treatment methods have evolved. Scientific research on automatic seizure detection started about 40 years ago [1]. The neurons generate electrical signals when they perceive stimuli from the environment or interact with each other for performing different activities [2]. The electrical signal generated by a single neuron is not strong enough to be detected. When a cluster of neurons act in concert, they generate an
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
